© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 22-GEMMASCOPE-2-RES-65K
    7. 8300
    Prev
    Next
    INDEX
    Explanations

    code imports

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_22_width_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     utils
    0.81
     amb
    0.79
     utilisez
    0.79
     organ
    0.78
     wiki
    0.76
     jeruk
    0.76
    昦
    0.76
     sais
    0.75
    
    0.75
     rumors
    0.75
    POSITIVE LOGITS
    I
    1.05
    ID
    1.01
    Я
    1.00
    IC
    1.00
    Fer
    0.97
    Ｉ
    0.95
    this
    0.93
    Max
    0.92
    II
    0.92
    Ко
    0.92
    Activations Density 0.003%

    No Known Activations